| Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding S Han, H Mao, WJ Dally arXiv preprint arXiv:1510.00149, 2015 | 7094 | 2015 |
| SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and< 0.5 MB model size FN Iandola, S Han, MW Moskewicz, K Ashraf, WJ Dally, K Keutzer arXiv preprint arXiv:1602.07360, 2016 | 6022 | 2016 |
| Learning both weights and connections for efficient neural network S Han, J Pool, J Tran, W Dally Advances in neural information processing systems 28, 2015 | 5000 | 2015 |
| Route packets, not wires: on-chip inteconnection networks WJ Dally, B Towles Proceedings of the 38th annual design automation conference, 684-689, 2001 | 4593 | 2001 |
| Principles and practices of interconnection networks WJ Dally, BP Towles Elsevier, 2004 | 4504 | 2004 |
| Deadlock-free message routing in multiprocessor interconnection networks WJ Dally, CL Seitz California Institute of Technology, 1988 | 2951 | 1988 |
| EIE: Efficient inference engine on compressed deep neural network S Han, X Liu, H Mao, J Pu, A Pedram, MA Horowitz, WJ Dally ACM SIGARCH Computer Architecture News 44 (3), 243-254, 2016 | 2330 | 2016 |
| Virtual-channel flow control WJ Dally IEEE Transactions on Parallel and Distributed systems 3 (2), 194-205, 1992 | 1928 | 1992 |
| Exascale computing study: Technology challenges in achieving exascale systems K Bergman, S Borkar, D Campbell, W Carlson, W Dally, M Denneau, ... Defense Advanced Research Projects Agency Information Processing Techniques …, 2008 | 1442 | 2008 |
| Performance analysis of k-ary n-cube interconnection networks WJ Dally IEEE transactions on Computers 39 (6), 775-785, 1990 | 1411 | 1990 |
| The torus routing chip WJ Dally, CL Seitz Distributed computing 1 (4), 187-196, 1986 | 1294* | 1986 |
| Digital systems engineering WJ Dally, WJ Dally, JW Poulton Cambridge university press, 1998 | 1288 | 1998 |
| Memory access scheduling S Rixner, WJ Dally, UJ Kapasi, P Mattson, JD Owens ACM SIGARCH Computer Architecture News 28 (2), 128-138, 2000 | 1281 | 2000 |
| The GPU computing era J Nickolls, WJ Dally IEEE micro 30 (2), 56-69, 2010 | 1233 | 2010 |
| Trained ternary quantization C Zhu, S Han, H Mao, WJ Dally arXiv preprint arXiv:1612.01064, 2016 | 980 | 2016 |
| SCNN: An accelerator for compressed-sparse convolutional neural networks A Parashar, M Rhu, A Mukkara, A Puglielli, R Venkatesan, B Khailany, ... ACM SIGARCH computer architecture news 45 (2), 27-40, 2017 | 910 | 2017 |
| Deep gradient compression: Reducing the communication bandwidth for distributed training Y Lin, S Han, H Mao, Y Wang, WJ Dally arXiv preprint arXiv:1712.01887, 2017 | 901 | 2017 |
| Deadlock-free adaptive routing in multicomputer networks using virtual channels WJ Dally, H Aoki IEEE transactions on Parallel and Distributed Systems 4 (4), 466-475, 1993 | 788 | 1993 |
| A delay model and speculative architecture for pipelined routers LS Peh, WJ Dally Proceedings HPCA seventh international symposium on high-performance …, 2001 | 726 | 2001 |
| GPUs and the future of parallel computing SW Keckler, WJ Dally, B Khailany, M Garland, D Glasco IEEE micro 31 (5), 7-17, 2011 | 721 | 2011 |
